Merge 7.3-rc5 into char-misc-next

Lots of subtrees are based on newer -rc versions, so sync up further on
the development cycle so that they can be cleanly merged into here.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

26 files changed, 163 insertions, 119 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index e57af902560c..1d2676782d70 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1651,8 +1651,9 @@ static inline void bpf_trampoline_set_flags(struct bpf_trampoline *tr, u32 flags
 struct bpf_func_info_aux {
 	u16 linkage;
 	bool unreliable;
-	bool called : 1;
-	bool verified : 1;
+	/* Indexed by in_sleepable. */
+	bool called[2];
+	bool verified[2];
 };
 
 enum bpf_jit_poke_reason {
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 36b65797877d..b83ec99f1a13 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -45,18 +45,20 @@ struct bpf_reg_state {
 	union {
 		/* valid when type == PTR_TO_PACKET */
 		int range;
+		/*
+		 * Valid when type == PTR_TO_STACK. Inside the callee two registers
+		 * can be both PTR_TO_STACK like R1=fp-8 and R2=fp-8, but one of them
+		 * points to this function stack while another to the caller's stack.
+		 * To differentiate them 'frameno' is used which is an index in
+		 * bpf_verifier_state->frame[] array pointing to bpf_func_state.
+		 */
+		u8 frameno;
 
-		/* valid when type == CONST_PTR_TO_MAP | PTR_TO_MAP_VALUE |
-		 *   PTR_TO_MAP_VALUE_OR_NULL
+		/*
+		 * For CONST_PTR_TO_MAP, PTR_TO_MAP_KEY, PTR_TO_MAP_VALUE and
+		 * PTR_TO_INSN.
 		 */
-		struct {
-			struct bpf_map *map_ptr;
-			/* To distinguish map lookups from outer map
-			 * the map_uid is non-zero for registers
-			 * pointing to inner maps.
-			 */
-			u32 map_uid;
-		};
+		struct bpf_map *map_ptr;
 
 		/* for PTR_TO_BTF_ID */
 		struct {
@@ -155,13 +157,12 @@ struct bpf_reg_state {
 	 * gets parent_id set to the dynptr's id.
 	 */
 	u32 parent_id;
-	/* Inside the callee two registers can be both PTR_TO_STACK like
-	 * R1=fp-8 and R2=fp-8, but one of them points to this function stack
-	 * while another to the caller's stack. To differentiate them 'frameno'
-	 * is used which is an index in bpf_verifier_state->frame[] array
-	 * pointing to bpf_func_state.
+	/*
+	 * Distinguishes inner-map lookups and their keys and values. Zero for
+	 * other registers. Kept outside the metadata union for ID remapping
+	 * during state comparisons.
 	 */
-	u32 frameno;
+	u32 map_uid;
 	/* if (!precise && SCALAR_VALUE) min/max/tnum don't affect safety */
 	bool precise;
 };
@@ -679,6 +680,7 @@ struct bpf_insn_aux_data {
 	bool nospec_result; /* result is unsafe under speculation, nospec must follow */
 	bool zext_dst; /* this insn zero extends dst reg */
 	bool needs_zext; /* alu op needs to clear upper bits */
+	bool prevent_zext; /* alu op cannot be zext (already used with 64-bit scalars) */
 	bool non_sleepable; /* helper/kfunc may be called from non-sleepable context */
 	bool is_iter_next; /* bpf_iter_<type>_next() kfunc call */
 	bool call_with_percpu_alloc_ptr; /* {this,per}_cpu_ptr() with prog percpu alloc */
@@ -1197,6 +1199,8 @@ static inline void bpf_trampoline_unpack_key(u64 key, u32 *obj_id, u32 *btf_id)
 
 int bpf_prepare_btf_info(struct bpf_verifier_env *env,
 			 const union bpf_attr *attr, bpfptr_t uattr);
+int bpf_check_core_relo(struct bpf_verifier_env *env,
+			const union bpf_attr *attr, bpfptr_t uattr);
 int bpf_check_btf_info(struct bpf_verifier_env *env,
 		       const union bpf_attr *attr, bpfptr_t uattr);
 
@@ -1236,11 +1240,18 @@ static inline int bpf_get_spi(s32 off)
 	return (-off - 1) / BPF_REG_SIZE;
 }
 
+/*
+ * Return the function state a stack pointer register refers to. frameno
+ * shares storage with other pointer metadata, so return NULL for any
+ * other register type instead of indexing frame[] with aliased bytes.
+ */
 static inline struct bpf_func_state *bpf_func(struct bpf_verifier_env *env,
 					      const struct bpf_reg_state *reg)
 {
 	struct bpf_verifier_state *cur = env->cur_state;
 
+	if (reg->type != PTR_TO_STACK)
+		return NULL;
 	return cur->frame[reg->frameno];
 }
 
diff --git a/include/linux/btf.h b/include/linux/btf.h
index 89d5a5c4f117..7c62ea17b116 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -80,6 +80,7 @@
 #define KF_ARENA_ARG2   (1 << 15) /* kfunc takes an arena pointer as its second argument */
 #define KF_IMPLICIT_ARGS (1 << 16) /* kfunc has implicit arguments supplied by the verifier */
 #define KF_SPINLOCK_SAFE (1 << 17) /* kfunc is allowed inside bpf_spin_lock-ed region */
+#define KF_PERFMON      (1 << 18) /* kfunc requires CAP_PERFMON */
 
 /*
  * Tag marking a kernel function as a kfunc. This is meant to minimize the
diff --git a/include/linux/console.h b/include/linux/console.h
index d624200cfc17..502d1abe3f50 100644
--- a/include/linux/console.h
+++ b/include/linux/console.h
@@ -173,7 +173,7 @@ static inline void con_debug_leave(void) { }
  * @CON_BRL:		Indicates a braille device which is exempt from
  *			receiving the printk spam for obvious reasons.
  * @CON_EXTENDED:	The console supports the extended output format of
- *			/dev/kmesg which requires a larger output buffer.
+ *			/dev/kmsg which requires a larger output buffer.
  * @CON_SUSPENDED:	Indicates if a console is suspended. If true, the
  *			printing callbacks must not be called.
  * @CON_NBCON:		Console can operate outside of the legacy style console_lock
diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h
index 158cd609f103..ffa99b930843 100644
--- a/include/linux/dma-fence.h
+++ b/include/linux/dma-fence.h
@@ -141,6 +141,9 @@ struct dma_fence_ops {
 	 * compute the name at runtime, without having it to store permanently
 	 * for each fence, or build a cache of some sort.
 	 *
+	 * The returned string is RCU protected and can be freed after the fence
+	 * signaled and a RCU grace period passed.
+	 *
 	 * This callback is mandatory.
 	 */
 	const char * (*get_driver_name)(struct dma_fence *fence);
@@ -153,6 +156,9 @@ struct dma_fence_ops {
 	 * having it to store permanently for each fence, or build a cache of
 	 * some sort.
 	 *
+	 * The returned string is RCU protected and can be freed after the fence
+	 * signaled and a RCU grace period passed.
+	 *
 	 * This callback is mandatory.
 	 */
 	const char * (*get_timeline_name)(struct dma_fence *fence);
diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index 6574b7183c01..fa2854fed1f2 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -102,7 +102,14 @@ static __always_inline long syscall_trace_enter(struct pt_regs *regs, unsigned l
 	if (unlikely(work & SYSCALL_WORK_SYSCALL_TRACEPOINT))
 		trace_syscall_enter(regs);
 
-	if (unlikely(audit_context()))
+	/*
+	 * The config check works around broken compilers which fail to
+	 * eliminate the dead code in case of CONFIG_AUDITSYSCALL=n as they
+	 * insist on creating a always false runtime condition based on
+	 * audit_context() which returns NULL in that case. The explicit
+	 * IS_ENABLED() check makes that madness go away.
+	 */
+	if (IS_ENABLED(CONFIG_AUDITSYSCALL) && unlikely(audit_context()))
 		syscall_enter_audit(regs);
 
 	return true;
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 12683b5d125e..c4c9ce038611 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -944,6 +944,7 @@ struct kernel_ethtool_ts_info {
 #define ETHTOOL_OP_NEEDS_RTNL_SPAUSEPARAM	BIT(6)
 #define ETHTOOL_OP_NEEDS_RTNL_RSS		BIT(7)
 #define ETHTOOL_OP_NEEDS_RTNL_GLINK		BIT(8)
+#define ETHTOOL_OP_NEEDS_RTNL_TEST		BIT(9)
 
 /**
  * struct ethtool_ops - optional netdev operations
@@ -981,6 +982,7 @@ struct kernel_ethtool_ts_info {
  *	 - netdev_update_features()
  *	 - netif_set_real_num_tx_queues()
  *	 - ethtool_op_get_link() (syncs link watch under rtnl_lock)
+ *	 - netif_open() / netif_close() (used by @self_test)
  *
  * @get_drvinfo: Report driver/device information. Modern drivers no
  *	longer have to implement this callback. Most fields are
@@ -1057,6 +1059,12 @@ struct kernel_ethtool_ts_info {
  * @get_sset_count: Get number of strings that @get_strings will write.
  * @get_rxnfc: Get RX flow classification rules.  Returns a negative
  *	error code or zero.
+ *	Note that for %ETHTOOL_GRXCLSRLALL rule_cnt and size of the arrays
+ *	is user-provided, and not guaranteed to match what driver would
+ *	have reported via %ETHTOOL_GRXCLSRLCNT. Drivers must return -%EMSGSIZE
+ *	when rule_cnt is too small. rule_locs is %NULL when rule_cnt is zero.
+ *	On success drivers must set rule_cnt to the number of locations they
+ *	filled in, the core copies out exactly that many.
  * @set_rxnfc: Set RX flow classification rules.  Returns a negative
  *	error code or zero.
  * @flash_device: Write a firmware image to device's flash memory.
diff --git a/include/linux/ieee80211-mesh.h b/include/linux/ieee80211-mesh.h
index 7eb15834531c..9e548b9173df 100644
--- a/include/linux/ieee80211-mesh.h
+++ b/include/linux/ieee80211-mesh.h
@@ -361,8 +361,7 @@ ieee80211_mesh_hwmp_perr_get_rcode(const u8 *ie, u8 dst_idx)
 /* IEEE Std 802.11-2016 9.4.2.113 PREQ element */
 static inline bool ieee80211_mesh_preq_size_ok(const u8 *pos, u8 elen)
 {
-	struct ieee80211_mesh_hwmp_preq_bottom *preq_elem_bottom =
-		ieee80211_mesh_hwmp_preq_get_bottom(pos);
+	struct ieee80211_mesh_hwmp_preq_bottom *preq_elem_bottom;
 	u8 target_count;
 	int needed;
 
@@ -378,6 +377,7 @@ static inline bool ieee80211_mesh_preq_size_ok(const u8 *pos, u8 elen)
 	if (elen < needed)
 		return false;
 
+	preq_elem_bottom = ieee80211_mesh_hwmp_preq_get_bottom(pos);
 	target_count = preq_elem_bottom->target_count;
 	/* IEEE Std 802.11-2016 Table 14-10 to 14-16 */
 	if (target_count < 1)
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 20cc16ea4e5a..4846032bf4ff 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -365,6 +365,9 @@ static inline int __vlan_insert_inner_tag(struct sk_buff *skb,
 	const u8 meta_len = mac_len > ETH_TLEN ? skb_metadata_len(skb) : 0;
 	struct vlan_ethhdr *veth;
 
+	if (unlikely(!pskb_may_pull(skb, mac_len)))
+		return -EINVAL;
+
 	if (skb_cow_head(skb, meta_len + VLAN_HLEN) < 0)
 		return -ENOMEM;
 
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 03bfc92864b6..cf7fe835c4ad 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -2324,13 +2324,18 @@ static inline bool kvm_test_request(int req, struct kvm_vcpu *vcpu)
 	return test_bit(req & KVM_REQUEST_MASK, (void *)&vcpu->requests);
 }
 
-static inline void kvm_clear_request(int req, struct kvm_vcpu *vcpu)
+static __always_inline void kvm_clear_request(int req, struct kvm_vcpu *vcpu)
 {
+	BUILD_BUG_ON(req == KVM_REQ_VM_DEAD);
+
 	clear_bit(req & KVM_REQUEST_MASK, (void *)&vcpu->requests);
 }
 
-static inline bool kvm_check_request(int req, struct kvm_vcpu *vcpu)
+static __always_inline bool kvm_check_request(int req, struct kvm_vcpu *vcpu)
 {
+	/* Once a VM is dead, it needs to stay dead. */
+	BUILD_BUG_ON(req == KVM_REQ_VM_DEAD);
+
 	if (kvm_test_request(req, vcpu)) {
 		kvm_clear_request(req, vcpu);
 
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 313e96173b19..48bde275968d 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -76,7 +76,7 @@ enum ata_quirks {
 	__ATA_QUIRK_MAX_SEC,		/* Limit max sectors */
 	__ATA_QUIRK_MAX_TRIM_128M,	/* Limit max trim size to 128M */
 	__ATA_QUIRK_NO_NCQ_ON_ATI,	/* Disable NCQ on ATI chipset */
-	__ATA_QUIRK_NO_LPM_ON_ATI,	/* Disable LPM on ATI chipset */
+	__ATA_QUIRK_NO_LPM_ON_ATI_AND_AMD, /* Disable LPM on ATI and AMD chipsets */
 	__ATA_QUIRK_NO_ID_DEV_LOG,	/* Identify device log missing */
 	__ATA_QUIRK_NO_LOG_DIR,		/* Do not read log directory */
 	__ATA_QUIRK_NO_FUA,		/* Do not use FUA */
@@ -115,7 +115,7 @@ enum {
 	ATA_QUIRK_MAX_SEC		= BIT_ULL(__ATA_QUIRK_MAX_SEC),
 	ATA_QUIRK_MAX_TRIM_128M		= BIT_ULL(__ATA_QUIRK_MAX_TRIM_128M),
 	ATA_QUIRK_NO_NCQ_ON_ATI		= BIT_ULL(__ATA_QUIRK_NO_NCQ_ON_ATI),
-	ATA_QUIRK_NO_LPM_ON_ATI		= BIT_ULL(__ATA_QUIRK_NO_LPM_ON_ATI),
+	ATA_QUIRK_NO_LPM_ON_ATI_AND_AMD	= BIT_ULL(__ATA_QUIRK_NO_LPM_ON_ATI_AND_AMD),
 	ATA_QUIRK_NO_ID_DEV_LOG		= BIT_ULL(__ATA_QUIRK_NO_ID_DEV_LOG),
 	ATA_QUIRK_NO_LOG_DIR		= BIT_ULL(__ATA_QUIRK_NO_LOG_DIR),
 	ATA_QUIRK_NO_FUA		= BIT_ULL(__ATA_QUIRK_NO_FUA),
diff --git a/include/linux/mempool.h b/include/linux/mempool.h
index a0fa6d43e0dc..6da502aef2f7 100644
--- a/include/linux/mempool.h
+++ b/include/linux/mempool.h
@@ -70,6 +70,13 @@ int mempool_alloc_bulk_noprof(struct mempool *pool, void **elem,
 #define mempool_alloc_bulk(...)						\
 	alloc_hooks(mempool_alloc_bulk_noprof(__VA_ARGS__))
 
+/*
+ * Allocate a new element without dipping into the pool's reserves or
+ * waiting.  Returns NULL on failure.
+ */
+#define mempool_alloc_noreserve(_pool, _gfp)				\
+	alloc_hooks((_pool)->alloc(_gfp, (_pool)->pool_data))
+
 void *mempool_alloc_preallocated(struct mempool *pool) __malloc;
 void mempool_free(void *element, struct mempool *pool);
 unsigned int mempool_free_bulk(struct mempool *pool, void **elem,
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 6d815f6440c9..f3e5a2fadbe5 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -1226,7 +1226,7 @@ struct mm_struct {
 		struct mm_mm_cid mm_cid;
 
 		/* sched_cache related statistics */
-		struct sched_cache_stat sc_stat;
+		struct sched_cache_group *sched_cache_grp;
 #ifdef CONFIG_MMU
 		atomic_long_t pgtables_bytes;	/* size of all page tables */
 #endif
@@ -1624,8 +1624,9 @@ static inline unsigned int mm_cid_size(void)
 #endif /* CONFIG_SCHED_MM_CID */
 
 #ifdef CONFIG_SCHED_CACHE
-void mm_init_sched(struct mm_struct *mm,
-		   struct sched_cache_time __percpu *pcpu_sched);
+int mm_init_sched(struct mm_struct *mm,
+		  struct sched_cache_time __percpu *pcpu_sched);
+void mm_destroy_sched(struct mm_struct *mm);
 
 static inline int mm_alloc_sched_noprof(struct mm_struct *mm)
 {
@@ -1635,17 +1636,11 @@ static inline int mm_alloc_sched_noprof(struct mm_struct *mm)
 	if (!pcpu_sched)
 		return -ENOMEM;
 
-	mm_init_sched(mm, pcpu_sched);
-	return 0;
+	return mm_init_sched(mm, pcpu_sched);
 }
 
 #define mm_alloc_sched(...)	alloc_hooks(mm_alloc_sched_noprof(__VA_ARGS__))
 
-static inline void mm_destroy_sched(struct mm_struct *mm)
-{
-	free_percpu(mm->sc_stat.pcpu_sched);
-	mm->sc_stat.pcpu_sched = NULL;
-}
 #else /* !CONFIG_SCHED_CACHE */
 
 static inline int mm_alloc_sched(struct mm_struct *mm) { return 0; }
diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h
index bec0eab6ef03..b8a13b8d36a4 100644
--- a/include/linux/mmap_lock.h
+++ b/include/linux/mmap_lock.h
@@ -630,6 +630,8 @@ static inline void mmap_read_unlock(struct mm_struct *mm)
 DEFINE_GUARD(mmap_read_lock, struct mm_struct *,
 	     mmap_read_lock(_T), mmap_read_unlock(_T))
 DEFINE_GUARD_COND(mmap_read_lock, _try, mmap_read_trylock(_T))
+DEFINE_GUARD(mmap_write_lock, struct mm_struct *,
+	     mmap_write_lock(_T), mmap_write_unlock(_T))
 
 static inline void mmap_read_unlock_non_owner(struct mm_struct *mm)
 {
diff --git a/include/linux/netfilter_arp/arp_tables.h b/include/linux/netfilter_arp/arp_tables.h
index 05631a25e622..8b8d472eff34 100644
--- a/include/linux/netfilter_arp/arp_tables.h
+++ b/include/linux/netfilter_arp/arp_tables.h
@@ -56,23 +56,4 @@ void arpt_unregister_table(struct net *net, const char *name);
 extern unsigned int arpt_do_table(void *priv, struct sk_buff *skb,
 				  const struct nf_hook_state *state);
 
-#ifdef CONFIG_NETFILTER_XTABLES_COMPAT
-#include <net/compat.h>
-
-struct compat_arpt_entry {
-	struct arpt_arp arp;
-	__u16 target_offset;
-	__u16 next_offset;
-	compat_uint_t comefrom;
-	struct compat_xt_counters counters;
-	unsigned char elems[];
-};
-
-static inline struct xt_entry_target *
-compat_arpt_get_target(struct compat_arpt_entry *e)
-{
-	return (void *)e + e->target_offset;
-}
-
-#endif /* CONFIG_COMPAT */
 #endif /* _ARPTABLES_H */
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index f837a501008c..b4dd32863dd4 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -246,6 +246,7 @@ struct netfs_io_request {
 	unsigned long long	submitted;	/* Amount submitted for I/O so far */
 	unsigned long long	len;		/* Length of the request */
 	size_t			transferred;	/* Amount to be indicated as transferred */
+	size_t			progress_at;	/* Report read progress when hit this much read */
 	long			error;		/* 0 or error that occurred */
 	unsigned long long	i_size;		/* Size of the file */
 	unsigned long long	start;		/* Start position */
@@ -262,7 +263,6 @@ struct netfs_io_request {
 	atomic_t		subreq_counter;	/* Next subreq->debug_index */
 	unsigned int		nr_group_rel;	/* Number of refs to release on ->group */
 	spinlock_t		lock;		/* Lock for queuing subreqs */
-	unsigned char		front_folio_order; /* Order (size) of front folio */
 	enum netfs_io_origin	origin;		/* Origin of the request */
 	bool			direct_bv_unpin; /* T if direct_bv[] must be unpinned */
 	refcount_t		ref;
@@ -275,9 +275,10 @@ struct netfs_io_request {
 #define NETFS_RREQ_SHORT_TRANSFER	5	/* Set if we have a short transfer */
 #define NETFS_RREQ_OFFLOAD_COLLECTION	8	/* Offload collection to workqueue */
 #define NETFS_RREQ_NO_UNLOCK_FOLIO	9	/* Don't unlock no_unlock_folio on completion */
-#define NETFS_RREQ_FOLIO_COPY_TO_CACHE	10	/* Copy current folio to cache from read */
+#define NETFS_RREQ_CANCEL_CACHING	10	/* Set to cancel caching */
 #define NETFS_RREQ_UPLOAD_TO_SERVER	11	/* Need to write to the server */
 #define NETFS_RREQ_USE_IO_ITER		12	/* Use ->io_iter rather than ->i_pages */
+#define NETFS_RREQ_NEED_PUT_RA_REFS	17	/* Need to put the folio refs RA gave us */
 #define NETFS_RREQ_USE_PGPRIV2		31	/* [DEPRECATED] Use PG_private_2 to mark
 						 * write to cache on read */
 	const struct netfs_request_ops *netfs_ops;
diff --git a/include/linux/ns/ns_common_types.h b/include/linux/ns/ns_common_types.h
index ea45c54e4435..6ed6b497831c 100644
--- a/include/linux/ns/ns_common_types.h
+++ b/include/linux/ns/ns_common_types.h
@@ -116,10 +116,8 @@ struct ns_common {
 	struct dentry *stashed;
 	const struct proc_ns_operations *ops;
 	unsigned int inum;
-	union {
-		struct ns_tree;
-		struct rcu_head ns_rcu;
-	};
+	struct ns_tree;
+	struct rcu_head ns_rcu;
 };
 
 #define to_ns_common(__ns)                                    \
diff --git a/include/linux/perf/riscv_pmu.h b/include/linux/perf/riscv_pmu.h
index f82a28040594..ecaa40370830 100644
--- a/include/linux/perf/riscv_pmu.h
+++ b/include/linux/perf/riscv_pmu.h
@@ -55,7 +55,7 @@ struct riscv_pmu {
 
 	irqreturn_t	(*handle_irq)(int irq_num, void *dev);
 
-	unsigned long	cmask;
+	DECLARE_BITMAP(cmask, RISCV_MAX_COUNTERS);
 	u64		(*ctr_read)(struct perf_event *event);
 	int		(*ctr_get_idx)(struct perf_event *event);
 	int		(*ctr_get_width)(int idx);
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 5842552294c1..915c6fd3f084 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1467,23 +1467,6 @@ static inline u32 perf_sample_data_size(struct perf_sample_data *data,
 	return size;
 }
 
-/*
- * Clear all bitfields in the perf_branch_entry.
- * The to and from fields are not cleared because they are
- * systematically modified by caller.
- */
-static inline void perf_clear_branch_entry_bitfields(struct perf_branch_entry *br)
-{
-	br->mispred	= 0;
-	br->predicted	= 0;
-	br->in_tx	= 0;
-	br->abort	= 0;
-	br->cycles	= 0;
-	br->type	= 0;
-	br->spec	= PERF_BR_SPEC_NA;
-	br->reserved	= 0;
-}
-
 extern void perf_output_sample(struct perf_output_handle *handle,
 			       struct perf_event_header *header,
 			       struct perf_sample_data *data,
diff --git a/include/linux/rbtree_augmented.h b/include/linux/rbtree_augmented.h
index 6dbc5a1bf6a8..d2fa1c41bfd2 100644
--- a/include/linux/rbtree_augmented.h
+++ b/include/linux/rbtree_augmented.h
@@ -87,18 +87,18 @@ rb_add_augmented_cached(struct rb_node *node, struct rb_root_cached *tree,
 }
 
 /*
- * Template for declaring augmented rbtree callbacks (generic case)
+ * Template for declaring augmented rbtree callbacks (generic multi fields)
  *
  * RBSTATIC:    'static' or empty
  * RBNAME:      name of the rb_augment_callbacks structure
  * RBSTRUCT:    struct type of the tree nodes
  * RBFIELD:     name of struct rb_node field within RBSTRUCT
- * RBAUGMENTED: name of field within RBSTRUCT holding data for subtree
- * RBCOMPUTE:   name of function that recomputes the RBAUGMENTED data
+ * RBCOPY:	name of function that copies the RBAUGMENTED datas
+ * RBCOMPUTE:   name of function that recomputes the RBAUGMENTED datas
  */
 
-#define RB_DECLARE_CALLBACKS(RBSTATIC, RBNAME,				\
-			     RBSTRUCT, RBFIELD, RBAUGMENTED, RBCOMPUTE)	\
+#define RB_DECLARE_CALLBACKS_MULTI(RBSTATIC, RBNAME,			\
+			     RBSTRUCT, RBFIELD, RBCOPY, RBCOMPUTE)	\
 static inline void							\
 RBNAME ## _propagate(struct rb_node *rb, struct rb_node *stop)		\
 {									\
@@ -114,14 +114,14 @@ RBNAME ## _copy(struct rb_node *rb_old, struct rb_node *rb_new)		\
 {									\
 	RBSTRUCT *old = rb_entry(rb_old, RBSTRUCT, RBFIELD);		\
 	RBSTRUCT *new = rb_entry(rb_new, RBSTRUCT, RBFIELD);		\
-	new->RBAUGMENTED = old->RBAUGMENTED;				\
+	RBCOPY(new, old);						\
 }									\
 static void								\
 RBNAME ## _rotate(struct rb_node *rb_old, struct rb_node *rb_new)	\
 {									\
 	RBSTRUCT *old = rb_entry(rb_old, RBSTRUCT, RBFIELD);		\
 	RBSTRUCT *new = rb_entry(rb_new, RBSTRUCT, RBFIELD);		\
-	new->RBAUGMENTED = old->RBAUGMENTED;				\
+	RBCOPY(new, old);						\
 	RBCOMPUTE(old, false);						\
 }									\
 RBSTATIC const struct rb_augment_callbacks RBNAME = {			\
@@ -131,6 +131,27 @@ RBSTATIC const struct rb_augment_callbacks RBNAME = {			\
 };
 
 /*
+ * Template for declaring augmented rbtree callbacks (generic single field)
+ *
+ * RBSTATIC:    'static' or empty
+ * RBNAME:      name of the rb_augment_callbacks structure
+ * RBSTRUCT:    struct type of the tree nodes
+ * RBFIELD:     name of struct rb_node field within RBSTRUCT
+ * RBAUGMENTED: name of field within RBSTRUCT holding data for subtree
+ * RBCOMPUTE:   name of function that recomputes the RBAUGMENTED data
+ */
+
+#define RB_DECLARE_CALLBACKS(RBSTATIC, RBNAME,				\
+			     RBSTRUCT, RBFIELD, RBAUGMENTED, RBCOMPUTE)	\
+static inline void							\
+RBNAME ## _copy_single(RBSTRUCT *new, RBSTRUCT *old)			\
+{									\
+	new->RBAUGMENTED = old->RBAUGMENTED;				\
+}									\
+RB_DECLARE_CALLBACKS_MULTI(RBSTATIC, RBNAME,				\
+		     RBSTRUCT, RBFIELD, RBNAME ## _copy_single, RBCOMPUTE)
+
+/*
  * Template for declaring augmented rbtree callbacks,
  * computing RBAUGMENTED scalar as max(RBCOMPUTE(node)) for all subtree nodes.
  *
diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index afc7daa6ee7d..eac3e9080c3c 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -3,8 +3,9 @@
 #define _LINUX_RING_BUFFER_H
 
 #include <linux/mm.h>
-#include <linux/seq_file.h>
 #include <linux/poll.h>
+#include <linux/ring_buffer_types.h>
+#include <linux/seq_file.h>
 
 #include <uapi/linux/trace_mmap.h>
 
@@ -279,11 +280,25 @@ static inline struct ring_buffer_desc *__first_ring_buffer_desc(struct trace_buf
 	return (struct ring_buffer_desc *)(&desc->__data[0]);
 }
 
+/*
+ * Returns the number of pages for a ring_buffer_desc. The caller must ensure it
+ * does not overflow ring_buffer_desc::nr_page_va.
+ */
+static inline unsigned long __calc_nr_pages_ring_buffer_desc(size_t size)
+{
+	/* Takes into account the reader page */
+	return max(DIV_ROUND_UP(size, PAGE_SIZE - BUF_PAGE_HDR_SIZE), 2UL) + 1;
+}
+
 static inline size_t trace_buffer_desc_size(size_t buffer_size, unsigned int nr_cpus)
 {
-	unsigned int nr_pages = max(DIV_ROUND_UP(buffer_size, PAGE_SIZE), 2UL) + 1;
+	unsigned long nr_pages = __calc_nr_pages_ring_buffer_desc(buffer_size);
 	struct ring_buffer_desc *rbdesc;
 
+	/* Capped by ring_buffer_desc::nr_page_va */
+	if (nr_pages > UINT_MAX)
+		return SIZE_MAX;
+
 	return size_add(offsetof(struct trace_buffer_desc, __data),
 			size_mul(nr_cpus, struct_size(rbdesc, page_va, nr_pages)));
 }
diff --git a/include/linux/rolling_buffer.h b/include/linux/rolling_buffer.h
index 9e5dad29669c..a97f7cfaacaa 100644
--- a/include/linux/rolling_buffer.h
+++ b/include/linux/rolling_buffer.h
@@ -45,9 +45,9 @@ struct rolling_buffer_snapshot {
 int rolling_buffer_init(struct rolling_buffer *roll, unsigned int rreq_id,
 			unsigned int direction, gfp_t gfp);
 int rolling_buffer_make_space(struct rolling_buffer *roll, gfp_t gfp);
-ssize_t rolling_buffer_load_from_ra(struct rolling_buffer *roll,
-				    struct readahead_control *ractl,
-				    struct folio_batch *put_batch);
+ssize_t rolling_buffer_bulk_load_from_ra(struct rolling_buffer *roll,
+					 struct readahead_control *ractl,
+					 unsigned int rreq_id, gfp_t gfp);
 ssize_t rolling_buffer_append(struct rolling_buffer *roll, struct folio *folio,
 			      unsigned int flags, gfp_t gfp);
 struct folio_queue *rolling_buffer_delete_spent(struct rolling_buffer *roll);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 8b3d47a325cc..d35ae49a991f 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1433,6 +1433,7 @@ struct task_struct {
 
 #ifdef CONFIG_SCHED_CACHE
 	struct callback_head		cache_work;
+	struct sched_cache_group __rcu	*sched_cache_grp;
 	int				preferred_llc;
 	/* 1: task was enqueued to its preferred LLC, 0 otherwise */
 	int				pref_llc_queued;
@@ -1787,7 +1788,7 @@ static inline bool is_lazy_mmu_mode_active(void)
 }
 #endif
 
-extern struct pid *cad_pid;
+extern struct pid __rcu *cad_pid;
 
 /*
  * Per process flags
@@ -2405,7 +2406,7 @@ struct sched_cache_time {
 	unsigned long epoch;
 };
 
-struct sched_cache_stat {
+struct sched_cache_group {
 	struct sched_cache_time __percpu *pcpu_sched;
 	raw_spinlock_t lock;
 	unsigned long epoch;
@@ -2413,11 +2414,26 @@ struct sched_cache_stat {
 	unsigned long next_scan;
 	unsigned long footprint;
 	int cpu;
+	refcount_t refcnt;
+	struct rcu_head rcu;
 } ____cacheline_aligned_in_smp;
 
+struct sched_cache_group *sched_cache_group_get(struct sched_cache_group *grp);
+struct sched_cache_group *task_cache_group_get(struct task_struct *p);
+
+void sched_cache_fork(struct task_struct *p);
+void sched_cache_fork_cleanup(struct task_struct *p);
+void sched_cache_exec_mmap(struct task_struct *p, struct mm_struct *mm);
+void sched_cache_exit_mm(struct task_struct *p);
+
 #else
 
-struct sched_cache_stat { };
+struct sched_cache_group { };
+
+static inline void sched_cache_fork(struct task_struct *p) { }
+static inline void sched_cache_fork_cleanup(struct task_struct *p) { }
+static inline void sched_cache_exec_mmap(struct task_struct *p, struct mm_struct *mm) { }
+static inline void sched_cache_exit_mm(struct task_struct *p) { }
 
 #endif
 
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index 584ae88b435e..d45a5476b97d 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -562,10 +562,7 @@ static inline sigset_t *sigmask_to_save(void)
 	return res;
 }
 
-static inline int kill_cad_pid(int sig, int priv)
-{
-	return kill_pid(cad_pid, sig, priv);
-}
+int kill_cad_pid(int sig, int priv);
 
 /* These can be the second arg to send_sig_info/send_group_sig_info.  */
 #define SEND_SIG_NOINFO ((struct kernel_siginfo *) 0)
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index b5d9d7c2b8ad..f96812d71c51 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -281,9 +281,9 @@ static inline int task_node(const struct task_struct *p)
 }
 
 #ifdef CONFIG_SCHED_CACHE
-extern void sched_update_llc_bytes(unsigned int cpu);
+extern void sched_update_llc_bytes(const struct cpumask *cpus);
 #else
-static inline void sched_update_llc_bytes(unsigned int cpu) { }
+static inline void sched_update_llc_bytes(const struct cpumask *cpus) { }
 #endif
 
 #endif /* _LINUX_SCHED_TOPOLOGY_H */
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 421f6fc45451..84308498a3a8 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1834,22 +1834,6 @@ static inline void skb_zcopy_set(struct sk_buff *skb, struct ubuf_info *uarg,
 	}
 }
 
-static inline void skb_zcopy_set_nouarg(struct sk_buff *skb, void *val)
-{
-	skb_shinfo(skb)->destructor_arg = (void *)((uintptr_t) val | 0x1UL);
-	skb_shinfo(skb)->flags |= SKBFL_ZEROCOPY_FRAG;
-}
-
-static inline bool skb_zcopy_is_nouarg(struct sk_buff *skb)
-{
-	return (uintptr_t) skb_shinfo(skb)->destructor_arg & 0x1UL;
-}
-
-static inline void *skb_zcopy_get_nouarg(struct sk_buff *skb)
-{
-	return (void *)((uintptr_t) skb_shinfo(skb)->destructor_arg & ~0x1UL);
-}
-
 static inline void net_zcopy_put(struct ubuf_info *uarg)
 {
 	if (uarg)
@@ -1872,8 +1856,7 @@ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy_success)
 	struct ubuf_info *uarg = skb_zcopy(skb);
 
 	if (uarg) {
-		if (!skb_zcopy_is_nouarg(skb))
-			uarg->ops->complete(skb, uarg, zerocopy_success);
+		uarg->ops->complete(skb, uarg, zerocopy_success);
 
 		skb_shinfo(skb)->flags &= ~SKBFL_ALL_ZEROCOPY;
 	}
@@ -4372,7 +4355,10 @@ skb_header_pointer_careful(const struct sk_buff *skb, int offset,
 static inline void * __must_check
 skb_pointer_if_linear(const struct sk_buff *skb, int offset, int len)
 {
-	if (likely(skb_headlen(skb) - offset >= len))
+	unsigned int uoffset = (unsigned int)offset;
+
+	if (likely(uoffset <= skb_headlen(skb) &&
+		   (unsigned int)len <= skb_headlen(skb) - uoffset))
 		return skb->data + offset;
 	return NULL;
 }